---
title: Basic Plots
output:
flexdashboard::flex_dashboard:
orientation: columns
self_contained: true
vertical_layout: scroll
theme: spacelab
source: embed
---
```{r}
knitr::opts_chunk$set(cache = TRUE, fig.align = 'center')
library(ggplot2)
library(ggthemes)
library(ggsci)
library(dplyr)
library(wordcloud)
library(tm)
```
# {.sidebar data-width=150}
#### Packages
* [ggplot2](https://ggplot2.tidyverse.org/reference/index.html)
* [ggsci](https://cran.r-project.org/web/packages/ggsci/vignettes/ggsci.html)
* ggthemes
* scales
* ggradar
* tm
* wordclouds
* dplyr
* plotly
# Data
##
### Dataset
```{r}
data("mtcars")
DT::datatable(mtcars)
```
##
### Description
The data was extracted from the 1974 _Motor Trend US magazine_, and comprises fuel consumption and 10 aspects of automobile design and performance for 32 automobiles (1973–74 models).
A data frame with 32 observations on 11 (numeric) variables.
**mpg** Miles/(US) gallon
**cyl** Number of cylinders
**disp** Displacement (cu.in.)
**hp** Gross horsepower
**drat** Rear axle ratio
**wt** Weight (1000 lbs)
**qsec** 1/4 mile time
**vs** Engine (0 = V-shaped, 1 = straight)
**am** Transmission (0 = automatic, 1 = manual)
**gear** Number of forward gears
**carb** Number of carburetors
# Bar plot
##
### Simple
```{r barplot1}
ggplot(mtcars, aes(cyl)) +
geom_bar(color = I("black"), fill = I("darkcyan")) +
xlab("Number of cylinders in a car") +
ylab("Number of cars")
```
##
### Stacked
```{r barplot2}
ggplot(mtcars, aes(cyl)) +
geom_bar(color = I("black"), aes(fill = factor(am))) +
xlab("Number of cylinders in a car") +
ylab("Number of cars")+
labs(fill = "Transmission")+
scale_fill_uchicago("dark")
```
# Histogramm
##
###
```{r}
ggplot(mtcars, aes(hp)) +
geom_histogram(color = I("black"), aes(fill = ..count..), binwidth = 25) +
xlab("Horsepower") +
ylab("Number of cars")
```
##
# Pie Chart
##
### Simple
```{r piechart}
ggplot(mtcars, aes(x = 1, y = sort(carb), fill = factor(sort(carb)))) +
geom_bar(stat = "identity") +
coord_polar(theta = "y") + labs(y = "Carburators", fill = "") +
theme(
axis.line=element_blank(),
axis.text.x=element_blank(),
axis.text.y=element_blank(),
axis.ticks=element_blank(),
axis.title.y=element_blank(),
panel.background=element_blank())+
scale_fill_aaas()
```
##
### Labeled
```{r}
# calculate a number of carbs in each group of cars with 2, 3, 4, ... carbrators
mt = mtcars %>% select(carb) %>%
mutate(carbFactor = factor(carb)) %>%
arrange(carbFactor) %>%
group_by(carbFactor) %>%
mutate(numCarbs = sum(carb))
# how much carburators in each group in %
mt = as.data.frame(mt)
mt$fracCarbs = round(mt$numCarbs/cumsum(mt$carb)[length(mt$carb)]*100, 1)
# select each group once for labeling
mt1 = as.data.frame(unique(mt))
ggplot(mt, aes(x = 1, y = carb) ) +
geom_bar(stat = "identity", aes(fill = carbFactor))+
geom_text(data = mt1, aes(x = 1.2, y = 94 - cumsum(numCarbs),
label = paste0(fracCarbs,"%")), size = 5) +
coord_polar(theta = "y") + labs(y = "Carburators", fill = "") +
theme(
axis.line=element_blank(),
axis.text.x=element_blank(),
axis.text.y=element_blank(),
axis.ticks=element_blank(),
axis.title.y=element_blank(),
panel.background=element_blank()) +
scale_fill_aaas()
```
# Scatter Plots
##
### Simple
```{r scatt}
ggplot(mtcars, aes(mpg, wt)) +
geom_point(aes(col = factor(cyl)), shape = 16, size = 4)+
xlab("Miles/(US) gallon") +
ylab("Weight (1000 lbs)") +
labs(color = "Cylinders") +
scale_color_aaas()
```
##
### With Regression Line
```{r scattregr}
ggplot(mtcars,aes(x=mpg,y=wt,color = factor(cyl)) ) + geom_point(shape = 16, size = 4) +
geom_smooth(method="lm", se= TRUE, color = "red") + xlab("Miles per Gallon ") +
ylab("Weight") + labs(colour = "Cylinders") + scale_color_aaas()
```
# Lines
##
### Multiple Layers + Legend
```{r lines}
data("EuStockMarkets")
EuStock <- as.data.frame(EuStockMarkets)
all_stocks <- ggplot() +
geom_line(data = EuStock,aes(x=c(1:nrow(EuStock)), y = DAX, color = 'DAX'),
size=1)+
geom_line(data = EuStock,aes(x=c(1:nrow(EuStock)), y = SMI, color='SMI'),
size =1)+
geom_line(data = EuStock,aes(x=c(1:nrow(EuStock)), y = CAC, color = 'CAC'),
size =1) +
geom_line(data = EuStock,aes(x=c(1:nrow(EuStock)),y = FTSE, color = 'FTSE'),
size =1) +
labs(x = "Days", y = "Price", colour = "Markets") +
scale_colour_aaas(guide = guide_legend(reverse = TRUE))
all_stocks
```
##
### Stock Markets Data
Daily Closing Prices of Major European Stock Indices, 1991–1998
```{r stockdata}
DT::datatable(EuStock)
```
# Word Clouds
##
### Centered
```{r wordcloud}
# download file
#download.file("https://ibm.box.com/shared/static/cmid70rpa7xe4ocitcga1bve7r0kqnia.txt",
# destfile = "./Data/churchill_speeches.txt", quiet = TRUE)
# Load the data as a corpus
dirPath <- "./Data/wordcloud"
speech <- Corpus(DirSource(dirPath))
# inspect the content
#inspect(speech)
# Data cleaning
# Convert the text to lower case
speech <- tm_map(speech, content_transformer(tolower))
# Remove numbers
speech <- tm_map(speech, removeNumbers)
# Remove english common stopwords
speech <- tm_map(speech, removeWords, stopwords("english"))
# Remove your own stop word
# specify your stopwords as a character vector
speech <- tm_map(speech, removeWords, c("floccinaucinihilipification", "squirrelled"))
# Remove punctuations
speech <- tm_map(speech, removePunctuation)
# Eliminate extra white
speech <- tm_map(speech, stripWhitespace)
# Create a Term Ducument Matric
dtm <-TermDocumentMatrix(speech)
# Convert to matric
m <- as.matrix(dtm)
# Sort
v <- sort(rowSums(m), decreasing = TRUE)
# Transform to a data frame
d <- data.frame(word = names(v), freq = v)
wordcloud(words = d$word, freq = d$freq, scale=c(5,.1), min.freq = 1, max.words = 175,
colors=brewer.pal(8, "Dark2"),
random.order = FALSE)
```
##
### Random
```{r wordcloud1}
wordcloud(words = d$word, freq = d$freq, scale=c(5,.1), min.freq = 1, max.words = 175,
colors=brewer.pal(8, "Dark2"),
random.order = TRUE)
```
###
[Text](https://ibm.box.com/shared/static/cmid70rpa7xe4ocitcga1bve7r0kqnia.txt)
# Radar Charts
##
###
```{r radarlibraries}
# download from the GitHub repository of the developer, Ricardo Bion
# devtools::install_github("ricardo-bion/ggradar", dependencies=TRUE)
library(ggradar)
library(scales)
```
```{r radardata}
#Select our dataset
mtcars %>%
#atribute rownames to a variable
add_rownames( var = "group" ) %>%
#assign each variable -- car names -- to their related variables
mutate_each(funs(rescale), -group) %>%
#select which data to plot
head(3) %>% select(1:10) -> mtcars_radar
```
```{r radarchart, fig.height=6, fig.width=9}
options(warn=-1)
ggradar(mtcars_radar)
```
##
# Box Plots
##
###
```{r boxplot}
ggplot(mtcars, aes(factor(cyl), mpg)) +
geom_boxplot(aes(fill = factor(cyl)) )+
xlab("Cylinders") + ylab("Miles per Gallon") +
scale_fill_aaas() +
#remove legend
theme(legend.position="none")
plotly:: ggplotly()
```
##
# Maps
##
### European Union
```{r ggplotmap}
states = read.csv("./Data/states.csv")
worldMap <- map_data("world")
states2 <- states %>% filter(European.Union == "Member") %>%
mutate(Country = as.character(Country))
worldMap1 <- worldMap %>%
mutate(region = ifelse(region == "UK", "United Kingdom", region)) %>%
arrange(desc(region) )
worldMap2 <- worldMap1 %>% filter(region %in% states2$Country)
europMap <- left_join(worldMap2, states2, by = c("region"="Country"))
ggplot(europMap, aes(x = long, y = lat, group = group, fill = factor(Accession.Year)) ) +
geom_polygon(color = "black") + labs(fill = "Accession Year") +
theme(
axis.line=element_blank(),
axis.text.x=element_blank(),
axis.text.y=element_blank(),
axis.ticks=element_blank(),
axis.title.y=element_blank(),
axis.title.x=element_blank(),
panel.background=element_blank()) +
scale_fill_aaas()
```
##
### Euro Zone
```{r ggplotmap2}
ggplot(europMap, aes(x = long, y = lat, group = group,
fill = factor(ifelse(Currency == 'Euro', 'Euro', 'Non-Euro'))) ) +
geom_polygon(color = "black") + labs(fill = 'Zone') +
theme(
axis.line=element_blank(),
axis.text.x=element_blank(),
axis.text.y=element_blank(),
axis.ticks=element_blank(),
axis.title.y=element_blank(),
axis.title.x=element_blank(),
panel.background=element_blank()) +
scale_fill_aaas()
```
